Claude Skills by Totes-MickGOATs

Migrate path-bound instruction blocks out of the root memory file into scoped .claude/rules/ files with paths frontmatter, so rules load when Claude reads matching files instead of taxing every session. Use for "my CLAUDE.md has rules only relevant to one folder", "set up .claude/rules", "scope my rules to paths", or as part of /opus-pocus. Probes harness support with a falsifiable token before migrating anything, then migrates one rule at a time — and knows what must stay in root (session-wi...

Audit blocking guards for over-reach — false positives that refuse legitimate work. Finds path resolution that treats out-of-scope paths as in-scope, guards applied to work outside the resource they protect, matching on symptom instead of emitter AND condition, missing or uncapped escape hatches, and block messages naming a route that no longer exists. Use for "the hook blocked something legitimate", "I can't write outside the repo", "this guard is in my way", "agents keep working around the ...

The ablation ritual — systematically remove instruction text and keep only removals that don't measurably hurt. Much instruction text is compensation for model weaknesses that no longer exist, and nobody measures which. Use for "is all this CLAUDE.md text even doing anything", "run an ablation", "my instructions grew for two years, prune them", or as a periodic maintenance pass after /opus-pocus. Requires a baseline (The Pensieve), a revert path, and an answer on whether humans read these fil...

Audit the repo's Claude instructions for vague rules — rules with no trigger, no scope, or no falsifiable condition. The 5-family reaches wider for instructions than older models, so a vague rule doesn't get ignored, it gets applied everywhere and dilutes the rules that matter. Use for "Claude over-applies my rules", "it keeps doing X when I only meant Y", "tighten up my CLAUDE.md", or as part of /opus-pocus. Read-only; rewrites each vague rule as trigger→action or recommends deletion. NOT fo...

Choose which Opus Pocus spells load in a session by writing per-skill `skillOverrides` entries to your settings, so a small repo carries three spells instead of all of them and pays only for what it uses. Detects the repo's shape, recommends a profile (greenfield / minimal / standard / full / maintenance), shows the exact settings diff, and writes only after you approve. Use for "which spells do I need", "opus pocus is too expensive", "turn off the spells I don't use", "configure opus pocus",...

Audit the repo's Claude instructions for contradictory rule pairs — rules where obeying one violates the other, or where a general rule and a specific rule collide with no stated precedence. The 5-family obeys widely, so it hits both rules of a contradiction and either freezes, alternates, or silently picks one. Use for "Claude is inconsistent about X", "it follows the rule sometimes", "these two docs disagree", or as part of /opus-pocus. Read-only; prescribes a carve-out, a kill, or a preced...

Audit every skill and agent description against the router's truncation cliff — the router selects on the description alone, listings truncate long descriptions (~1,500 chars in some harnesses), and routing-critical clauses written last silently vanish. Use for "the wrong agent keeps getting picked", "my skill never triggers", "NOT-for clauses aren't working", "right-size my descriptions", or as part of /opus-pocus. Reports per-description length, what the router actually sees, and a reordere...

Audit the repo's Claude instructions for self-correction death spirals — verify-your-work prompts, Stop/advisory hooks that re-fire on unchanged state, unbounded review→fix→re-review loops, and obligations that can never be discharged. Use for "Claude keeps re-checking itself", "the session never ends", "hooks keep waking it up", "it loops on verification", or as part of /opus-pocus. Read-only; reports findings with file:line and a fix per class. NOT for debugging application-level infinite l...

Fetch the CURRENT official and community guidance on structuring repos for Claude's newest models before auditing or changing anything — Anthropic docs, the Claude Code changelog, and credible practitioner writing. Best practices for the 5-family are still being figured out in public and drift fast; an audit calibrated on stale lore prescribes stale fixes. Use at the start of /opus-pocus, or for "what's the latest guidance", "are we following current best practice", "has Anthropic said anythi...

Measure and reduce per-prompt hook injection — the context every hook adds to every turn (SessionStart, UserPromptSubmit, PostToolUse, Stop advisories). Ranks emitters by tokens injected, finds false-positive matchers (bad keyword regexes, over-broad triggers), and prescribes fixes so hooks speak when relevant and stay silent otherwise. Use for "my context fills up instantly", "hooks are spamming every prompt", "dispatch hints are always wrong", "cut my token overhead", or as part of /opus-po...

Audit whether every check in the repo can tell "passed" apart from "never ran" — empty input reported as clean, filters that narrow the verdict as well as the output, exit codes read where the artifact is the evidence, skipped steps reported as passed, and reports with no denominator. Use for "the lint says clean but the bug shipped", "did that check actually run", "the test filter matched nothing", "green build, broken tree", "why did nothing get flagged", or as part of /opus-pocus. Read-onl...

Put memory files (CLAUDE.md, AGENTS.md) on a diet — find fossils (migration-relative phrasing, "this used to say X" narratives, dated retractions living in the hot path), typed facts that drift (hand-written counts, sizes, versions), and history that belongs in an archive. The 5-family reads the whole file every session; every stale or historical sentence is context spent steering nothing. Use for "my CLAUDE.md is huge", "Claude cites outdated facts", "clean up my memory file", or as part of ...

The grand ritual — run the Opus Pocus audit passes over this repo's Claude instruction layer (memory files, hooks, skills, agents) and its automation layer, then emit The O.W.L. report with a grade per spell and a fix table you approve from. Triages first, so passes with no subject in your repo are marked N/A rather than run. Use for "audit this repo for Opus 5", "run opus pocus", "de-hex this repo", "why does Opus behave badly here", or any request to modernize Claude instructions for the 5-...

Audit whether every automation artifact is actually reached — hooks whose declared event does not match their wiring, orphaned skills/agents/commands/tests, artifacts that exist but nothing ever causes to run, and artifacts that work only because of local state a fresh clone lacks. Use for "is this hook even firing", "did my skill ever run", "find orphaned automation", "why did nothing happen", "this lint has never caught anything", or as part of /opus-pocus. Read-only; reports per-artifact d...

Install a write-time hook that checks instruction artifacts as they are edited, so the defects the audit passes hunt stop accumulating between rituals — the one spell in this book that ships a mechanism rather than prose. Runs only the checks a script can decide without a model: emphasis inflation, descriptions past the truncation cliff, undeclared agent model tiers, rule globs matching nothing, memory files over a size ceiling. Use for "stop this happening again", "enforce the opus pocus rul...

Audit the repo's Claude instructions for emphasis that over-applies on the 5-family — CRITICAL/YOU MUST/NEVER-EVER incantations, all-caps sentences, threats, and stacked warnings. The 5-family over-obeys emphasis: shouted rules get treated as globally binding while calm rules get under-weighted; when everything is shouted, nothing is prioritized. Use for "Claude fixates on one rule", "it ignores my other instructions", "tone down my CLAUDE.md", or as part of /opus-pocus. Read-only; prescribes...

Audit and assign model tiers to every agent in the repo — classify each as planner, builder, or judge, and pin an explicit model per role so expensive models plan and judge while cheaper models execute. Use for "which agents should run on which model", "cut my token spend", "set up model tiers", "Opus is doing grunt work", or as part of /opus-pocus. Reports the classification table and the frontmatter edits; prescribes a lint so future agents must declare a tier. NOT for choosing the user's i...

Apply a model-era delta to this repo's instruction layer — establish from evidence which model family the files were written for, then list what current guidance changes, as edits to your files rather than as research. Use for "these instructions were written for an older model", "what changed for the 5-family", "are we still writing for Sonnet 3.5", "is any of this advice out of date", "we have a model ID hardcoded somewhere", or as part of /opus-pocus. Consumes legilimens-anthropica's diges...

Instrument the repo for a measurement week after instruction-layer changes — count what actually happens (advisory re-fires, review-loop rounds, subagent bounces, tokens injected per prompt, session outcomes) so the next round of changes is decided by numbers, not vibes. Use after landing /opus-pocus fixes, before/after any Avada Verbosa ablation round, or for "did those CLAUDE.md changes help", "measure Claude's behavior in this repo", "set up instruction telemetry". Produces the counter lis...

Mine the repo's own session transcripts for places the human corrected the agent, cluster them, and derive which instruction is missing, wrong, or being ignored — the evidence-first inverse of every other pass, which read text and reason about it. Use for "what do I keep having to tell it", "why does it ignore that rule", "what belongs in my memory file that isn't there", "which of my rules has never once mattered", or as part of /opus-pocus. Reads local transcripts in place, quotes minimally...

Author a first memory file for a repo that has none — derived from the repo's actual build/test commands, its real conventions, and its correction history, never invented. The one generative pass in this book: it proposes a file, you approve it, exactly like any other fix-table row. Use for "this repo has no CLAUDE.md", "write me a starter memory file", "set up Claude for this project", "what should my AGENTS.md say", or when a triage finds no instruction layer to audit. Deliberately small — ...